BRN Discussion Ongoing

stockduck

Regular
Is here someone who could explain me how they reach that performance of their chip?



:unsure:

  • Directly addresses technology and economic barriers to AI adoption via streamlined processing that yields 10-100x improvement in systems efficiency, lower latency, lower energy, and reduced size and cost

"....
Quotes from Industry Analysts, Investors and Customers:

“Blaize is very innovative, our important business partner,” says Yukihide Niimi, CEO of NSITEXE and DENSO Advisory Board member. “DENSO is demonstrating leadership in many areas as the automotive industry undergoes extraordinary technology changes. NSITEXE was established to catch up such technology change and to accelerate development of flexible compute IP solutions like DFP. NSITEXE is willing to work together with Blaize to boost the flexible Graph (Data Flow) compute technology eco-system.”
....."
Sorry if mention before..........but is it diffrent to Akida IP?
 
  • Like
  • Thinking
Reactions: 5 users

TopCat

Regular
iCatch have been working with Prophesee and Sony to develop their SoC. Maybe ( hope ) we are involved. What car maker?

iCatch Technology provides driver monitoring system (DMS) solutions​

iCatch's Intelligent Imaging SoC has been selected by a leading European car maker as the core processor of its DMS and has already entered mass production.

iCatch has co-developed EVS-based intelligent vision processing system with Sony Semiconductor Solutions (SSS) and Prophesee. When this solution is applied to DMS application, not only can it track driver's gaze and alertness with high accuracy and fast response rate using the embedded deep learning accelerator but also can protect driver's privacy.
Considering our great mutual partnership with Prophesee would we naturally be involved with this partnership or are iCatch only using Prophesee in another way…I’m confused here 🤔. This article from May but noting now that this chip has recently been mass produced into a European car manufacturer for their driver monitoring system. 🤞
12D8E92E-70A0-4754-A683-78E78739E475.jpeg


Now iCatch has collaborated with Prophesee on Event-based Metavision sensing projects that integrated iCatch’s V57 AI vision processor with the new Sony Semiconductor Solutions (“SSS”) stacked Event-based Vision Sensor IMX636, realized in collaboration between SSS and Prophesee.
iCatch built the OpenMVCam development platform for all algorithm partners and ODM customers to design a variety of AI products, systems and applications on many market segments like surveillance, smart healthcare, in-cabin monitor system, smart home, industrial automation, smart city and so on.

SSS’s Event-based Vision Sensor can be the input source for iCatch AI vision processor, based on iCatch built-in NPU acceleration engine and proprietary CV processing hardware engine. It can integrate Prophesee Metavision Intelligence SDK and other 3rd party’s machine vision algorithms to support end customers’ AI vision applications such as DMS and OMS in automotive in-cabin, patient/elder fall detection in home healthcare and hospitals, intruder detection in home surveillance, anomaly detection in industrial automation, gesture control in smart home appliance, eye tracking in AR/VR and so on.

 
  • Like
  • Thinking
  • Fire
Reactions: 20 users

JK200SX

Regular
  • Like
  • Haha
  • Fire
Reactions: 13 users

Dang Son

Regular
I just worked out why Blind Freddie was so dismissive of my question. It was because of this statement by Douglas Fairbairn Director of Business Development for MegaChips USA:

“What people have found is that the existing processors from ARM or RISC-V do not address the power performance requirements of the AI industry.”

It of course makes clear why ARM and SiFive both jumped virtually together to announce partnerships with Brainchip.

It was so they could “address the power performance requirements of the Ai industry.”

Now I get it.😂🤣😂🤣😂

Blind Freddie shakes his head and walks away.

My opinion only DYOR
FF

AKIDA BALLISTA
Hey FF , would you consider attending the Sydney Uni New Ro Mor Phick event to help the class grasp the significance of our latest patent grant? 😃
 
  • Like
  • Haha
  • Fire
Reactions: 9 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
A UVA Researcher is working on smart image sensor system which mimics the human eye. I wonder who's neuromorphic chip he's using? It states "A software and hardware co-designed artificial neural network completes the sensor system. An artificial synapse, called the memristor, moves pre-processed sensory inputs to the brain of the system, a neuromorphic chip that can perform high-level signal processing."

 
  • Like
  • Fire
  • Wow
Reactions: 7 users

JK200SX

Regular
Hey FF , would you consider attending the Sydney Uni New Ro Mor Phick event to help the class grasp the significance of our latest patent grant? 😃


"New Ro Mor Phick" - is that Vietnamese :ROFLMAO:

 
  • Haha
  • Like
  • Love
Reactions: 8 users

  • Directly addresses technology and economic barriers to AI adoption via streamlined processing that yields 10-100x improvement in systems efficiency, lower latency, lower energy, and reduced size and cost

"....
Quotes from Industry Analysts, Investors and Customers:

“Blaize is very innovative, our important business partner,” says Yukihide Niimi, CEO of NSITEXE and DENSO Advisory Board member. “DENSO is demonstrating leadership in many areas as the automotive industry undergoes extraordinary technology changes. NSITEXE was established to catch up such technology change and to accelerate development of flexible compute IP solutions like DFP. NSITEXE is willing to work together with Blaize to boost the flexible Graph (Data Flow) compute technology eco-system.”
....."
Sorry if mention before..........but is it diffrent to Akida IP?
Hi @stockduck

I don’t know how they do it but what they do is nowhere up to the Brainchip AKIDA standard of 1,000 times more energy efficient than a GPU at uni watts and milli watts of power:

“Smaller than the size of a credit card, the P1600 operates with 50x lower memory bandwidth, 7 W of power at 16 TOPS, 10x lower latency, and 30x better efficiency than legacy GPUs – opening doors to previously unfeasible”

Beware of wolves in sheep clothing particularly when running at the Edge. 🤣😂🤣🤡

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Fire
  • Love
Reactions: 23 users
That would mean that institutions and mutual funds have now acquired approx 196 million shares (~11.5% of shares on issue).

View attachment 18700
That is very greedy of them they must subscribe to the Warren Buffet school of investment theory.

There are the quick and there are the unresearched, no conviction, get rich quick retail sold out dead.

My opinion only DYOR
FF

AKIDA BALLISTA

PS: A little bird has told me only this morning that the huge advantage of SNN Edge computing is finally gaining real traction in the academic world. Making every sensor smart is becoming a sensible mainstream idea.

Leaving aside the pretenders there is one company waiting in a climbing hammock on the cliff face for the World to arrive.
 
  • Like
  • Love
  • Fire
Reactions: 35 users

stockduck

Regular
Thank you fact finder for your evaluation, I was a little unsecure because they tell about 7 W for the hole system P 1600 and not the single chip on board of the system.....I don`t know.
 
  • Like
  • Love
Reactions: 6 users

Dhm

Regular
Apologies if previously published.

I found this video of tinyML Neuromorphic Engineering Forum, Systems Session from 9th October. Much of it is a little over my head, however Anil Mankar speaks from the 31m 50s part.



One particular part of his talk centered around power consumption, and it highlights that the time is now up to continue using power hungry systems:
Screen Shot 2022-10-13 at 9.08.32 am.png
 
  • Like
  • Love
  • Fire
Reactions: 19 users

Dozzaman1977

Regular
I think this is new , just put on website

Portfolio with New Awards and IP Acquisition

Laguna Hills, Calif. – DATE, 2022 BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI IP, has extended the breadth and depth of its neuromorphic IP with two new patents granted by the US Patents and Trademarks Office (USPTO), and the acquisition of previously licensed technology from Toulouse Tech Transfer (TTT). These latest additions of technical assets reinforce BrainChip’s event-based processor differentiation for high performance, ultra-low power AI inference and on-chip learning.

The latest patents awarded to BrainChip from the USPTO include:

  • US 11,468,299 “An Improved Spiking Neural Network,” protects the learning function of BrainChip’s digital neuron circuit implemented on a neuromorphic integrated circuit/system (e.g., AkidaTM).
  • US 11,429,857, “Secure Voice Communications System,” protects a system to establish secure voice communications between a local and a remote neural network device. Information is encrypted by transmitting spike timing rather than original data, rendering it useless to anyone intercepting the transmission.
BrainChip also acquired full ownership of the IP rights related to JAST learning rule and algorithms from French technology transfer-based company TTT, including issued patent EP3324344 and pending patents US2019/0286944 and EP3324343. The invention related to the acquired IP rights include pattern detection algorithms that provide BrainChip with significant competitive advantages. The company held an exclusive license for the IP prior to their acquisition.

BrainChip considers patents to be valuable IP assets that help the company preserve its global competitive advantages. Its patent portfolio now comprises 10 US, 1 European and 1 Chinese issued patents. In addition, some 28 patent applications are pending in the US, Europe, Australia, Canada, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 66 users

Deadpool

hyper-efficient Ai
Nice quote from Andrew Carnegie going forward fellow chippers.

"And while the law of competition may be sometimes hard for the individual, it is best for the race, because it ensures the survival of the fittest in every department".

Not that we have any real competition:whistle:
 
  • Like
  • Love
  • Fire
Reactions: 14 users
I think this is new , just put on website

Portfolio with New Awards and IP Acquisition

Laguna Hills, Calif. – DATE, 2022 BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI IP, has extended the breadth and depth of its neuromorphic IP with two new patents granted by the US Patents and Trademarks Office (USPTO), and the acquisition of previously licensed technology from Toulouse Tech Transfer (TTT). These latest additions of technical assets reinforce BrainChip’s event-based processor differentiation for high performance, ultra-low power AI inference and on-chip learning.

The latest patents awarded to BrainChip from the USPTO include:

  • US 11,468,299 “An Improved Spiking Neural Network,” protects the learning function of BrainChip’s digital neuron circuit implemented on a neuromorphic integrated circuit/system (e.g., AkidaTM).
  • US 11,429,857, “Secure Voice Communications System,” protects a system to establish secure voice communications between a local and a remote neural network device. Information is encrypted by transmitting spike timing rather than original data, rendering it useless to anyone intercepting the transmission.
BrainChip also acquired full ownership of the IP rights related to JAST learning rule and algorithms from French technology transfer-based company TTT, including issued patent EP3324344 and pending patents US2019/0286944 and EP3324343. The invention related to the acquired IP rights include pattern detection algorithms that provide BrainChip with significant competitive advantages. The company held an exclusive license for the IP prior to their acquisition.

BrainChip considers patents to be valuable IP assets that help the company preserve its global competitive advantages. Its patent portfolio now comprises 10 US, 1 European and 1 Chinese issued patents. In addition, some 28 patent applications are pending in the US, Europe, Australia, Canada, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.
Just brilliant. I had not seen this information presented so clearly.
Many thanks @Dozzaman1977

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Fire
Reactions: 25 users

Slade

Top 20
I think this is new , just put on website

Portfolio with New Awards and IP Acquisition

Laguna Hills, Calif. – DATE, 2022 BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI IP, has extended the breadth and depth of its neuromorphic IP with two new patents granted by the US Patents and Trademarks Office (USPTO), and the acquisition of previously licensed technology from Toulouse Tech Transfer (TTT). These latest additions of technical assets reinforce BrainChip’s event-based processor differentiation for high performance, ultra-low power AI inference and on-chip learning.

The latest patents awarded to BrainChip from the USPTO include:

  • US 11,468,299 “An Improved Spiking Neural Network,” protects the learning function of BrainChip’s digital neuron circuit implemented on a neuromorphic integrated circuit/system (e.g., AkidaTM).
  • US 11,429,857, “Secure Voice Communications System,” protects a system to establish secure voice communications between a local and a remote neural network device. Information is encrypted by transmitting spike timing rather than original data, rendering it useless to anyone intercepting the transmission.
BrainChip also acquired full ownership of the IP rights related to JAST learning rule and algorithms from French technology transfer-based company TTT, including issued patent EP3324344 and pending patents US2019/0286944 and EP3324343. The invention related to the acquired IP rights include pattern detection algorithms that provide BrainChip with significant competitive advantages. The company held an exclusive license for the IP prior to their acquisition.

BrainChip considers patents to be valuable IP assets that help the company preserve its global competitive advantages. Its patent portfolio now comprises 10 US, 1 European and 1 Chinese issued patents. In addition, some 28 patent applications are pending in the US, Europe, Australia, Canada, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.
New and by the sound of it, very significant. Thanks for sharing @Dozzaman1977
 
  • Like
  • Fire
  • Love
Reactions: 21 users
1665614320497.png
 
  • Like
  • Fire
  • Wow
Reactions: 26 users
Not sure what this is about but Jeremy liked it and it has Tesla, SNN and spikes in the same sentence?

1665614639451.png
 
  • Like
  • Fire
  • Wow
Reactions: 27 users
Not sure what this is about but Jeremy liked it and it has Tesla, SNN and spikes in the same sentence?

View attachment 18707
A little birdie told me that it is a big deal for this Professor to come out of the closet in favour of SNN technology, supporting the shifting of compute to the Edge by making every sensor smart and criticising the old school 500 watt guzzling Dojo built by Tesla as the redundant past dinosaur type thinking that has no place in the future.

He is also completely independent of Brainchip.

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Love
  • Fire
Reactions: 58 users

buena suerte :-)

BOB Bank of Brainchip
ANNOUNCEMENT !!!!

BrainChip Strengthens Patent Portfolio • BrainChip acquires previously licenced JAST learning rule technology, including licenced patents


Patents Acquisition of Prior Licensed Technology from Toulouse Tech Transfer (“TTT” or “Licensor”): In 2017, BrainChip acquired an exclusive licence for the JAST learning rule and algorithms from French technology transfer-based company TTT. The JAST learning rule and algorithms were developed by Brain and Cognition Research Centre (CERCO), a preeminent public research lab based in Toulouse, France (CNRS/Université Toulouse III Paul Sabatier laboratory), and the Spanish National Research Council (CSIC), the largest public research institution in Spain and one of the most renowned institutions in the European Research Area. BrainChip has now acquired full ownership of the IP rights related to the JAST learning rule and algorithms and terminated the licence agreement. Some highlights of the transaction: • BrainChip acquired patents/patent applications - EP3324344 (issued), US2019/0286944 (pending) and EP3324343 (pending). The formalities related to the assignment of these patents/patent applications at the corresponding patent offices will take place soon. • BrainChip paid a one-off fee of €250,000 to acquire the patents/patent applications and terminate the licence agreement. With this, BrainChip has no further obligations to the licensor and expects cost savings in the long run by owning the IP. • BrainChip believes the pending patent applications, once issued, will protect a broad level of learning algorithms, providing competitive advantages to the Company
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 53 users
Just brilliant. I had not seen this information presented so clearly.
Many thanks @Dozzaman1977

My opinion only DYOR
FF

AKIDA BALLISTA
Get ready for an announcement incoming.

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Fire
  • Love
Reactions: 24 users

HopalongPetrovski

I'm Spartacus!
We now "own" JAST!
Yeah Baby!
 
  • Like
  • Love
  • Fire
Reactions: 40 users
Top Bottom